TY - JOUR
T1 - Comparison study of transfer function and artificial neural network for cash flow analysis at Bank Rakyat Indonesia
AU - Faricha, Anifatul
AU - Ulyah, Siti Maghfirotul
AU - Susanti, Rika
AU - Mardhiana, Hawwin
AU - Nanda, Muhammad Achirul
AU - Amira Rahmayanti, Ilma
AU - Andreas, Christopher
N1 - Funding Information:
Siti Maghfirotul Ulyah is a junior lecturer at the Department of Mathematics Universitas Airlangga. She finished her bachelor's study in Statistics, Institut Teknologi Sepuluh Nopember in 2014. Then, she continued her master's degree in Finance at National Taiwan University of Science and Technology. She was awarded the scholarship from the Ministry of Religious Affairs Indonesia during her undergraduate study and scholarship from NTUST for her master's study. Her research interest is in financial statistics, stochastic modelling, and time series analysis. Now, she is doing her PhD in Mathematics at Khalifa University, UAE. She can be contacted at email: maghfirotul.ulyah@fst.unair.ac.id.
Funding Information:
Ilma Amira Rahmayanti is a bachelor's student at the Department of Mathematics, Faculty of Science and Technology, Universitas Airlangga, Surabaya, Indonesia. During her undergraduate study, she was awarded Academic Achievement Improvement (PPA) Scholarship by the Ministry of Research, Technology, and Higher Education Indonesia. She is also a personal assistant of the speaker at the 8th International Conference and Workshop on Basic and Applied Science. Currently, she is working on her bachelor project in the field of data mining with decision tree algorithms. Her research interest is in business analytics and time series analysis. She can be contacted at email: ilma.amira.rahmayanti-2018@fst.unair.ac.id.
Publisher Copyright:
© 2022 Institute of Advanced Engineering and Science. All rights reserved.
PY - 2022/12
Y1 - 2022/12
N2 - The cash flow analysis is essential to examine the economic flows in the financial system. In this paper, the financial dataset at Bank Rakyat Indonesia was used, it recorded the sources of cash inflow and outflow during a particular period. The univariate time series model like the autoregressive and integrated moving average is the common approach to build the prediction based on the historical dataset. However, it is not suitable to estimate the multivariate dataset and to predict the extreme cases consisting of nonlinear pairs between independent-dependent variables. In this study, the comparison of using two types of models i.e., transfer function and artificial neural network (ANN) were investigated. The transfer function model includes the coefficient of moving average (MA) and autoregressive (AR), which allows the multivariate analysis. Furthermore, the artificial neural network allows the learning paradigm to achieve optimal prediction. The financial dataset was divided into training (70%) and testing (30%) for two types of models. According to the result, the artificial neural network model provided better prediction with achieved root mean square error (RMSE) of 0.264897 and 0.2951116 for training and testing respectively.
AB - The cash flow analysis is essential to examine the economic flows in the financial system. In this paper, the financial dataset at Bank Rakyat Indonesia was used, it recorded the sources of cash inflow and outflow during a particular period. The univariate time series model like the autoregressive and integrated moving average is the common approach to build the prediction based on the historical dataset. However, it is not suitable to estimate the multivariate dataset and to predict the extreme cases consisting of nonlinear pairs between independent-dependent variables. In this study, the comparison of using two types of models i.e., transfer function and artificial neural network (ANN) were investigated. The transfer function model includes the coefficient of moving average (MA) and autoregressive (AR), which allows the multivariate analysis. Furthermore, the artificial neural network allows the learning paradigm to achieve optimal prediction. The financial dataset was divided into training (70%) and testing (30%) for two types of models. According to the result, the artificial neural network model provided better prediction with achieved root mean square error (RMSE) of 0.264897 and 0.2951116 for training and testing respectively.
KW - Artificial neural network
KW - Cash flow
KW - Multivariate
KW - Time series
KW - Transfer function
UR - http://www.scopus.com/inward/record.url?scp=85139063145&partnerID=8YFLogxK
U2 - 10.11591/ijece.v12i6.pp6635-6644
DO - 10.11591/ijece.v12i6.pp6635-6644
M3 - Article
AN - SCOPUS:85139063145
SN - 2088-8708
VL - 12
SP - 6635
EP - 6644
JO - International Journal of Electrical and Computer Engineering
JF - International Journal of Electrical and Computer Engineering
IS - 6
ER -